SKSmita Krishnaswamy

Smita Krishnaswamy

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Smita Krishnaswamy has a total of 711 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    GeoSinkhorn Flow: Geometry-Aware Flow Matching for Perturbation-Conditioned Dynamics in Single cell Data Phenoscapes

    by Ke Xu, Alistair Wilkinson, Shuang Ni, Guillaume Huguet, Mark Gerstein, Guy Wolf, Christopher J. Tape, Smita Krishnaswamy

    Single-cell technologies increasingly enable large-scale profiling of complex biological systems across many experimental perturbations, but understanding how a system reorganizes across an entire space of conditions is difficult to interpret from single-cell embeddings alone. Phenoscapes address this by embedding entire cell-state distributions, rather than individual cells, as points in a data-driven landscape. Thus, a single dot represents one experimental condition rather than one cell, yielding a map of the perturbation or patient landscape that reveals how phenotype varies continuously across conditions. Phenoscapes remain a comparatively new and underexplored representation and existing static phenoscapes position experimental conditions relative to one another without specifying trajectories that describe how a cellular population moves from one condition to another. Flow- and trajectory-based models for single-cell data are numerous, but existing approaches operate at the level of individual cells, are not built to respect the geometry of a phenoscape, and typically cannot generalize their predicted flows to conditions not seen during training. Here we introduce GeoSinkhorn Flow, a perturbation-conditioned, geometry-aware flow-matching framework specialized designed to convert a static phenoscape into a dynamic phenoscape, in which each condition-level point is additionally connected by geodesic, condition-aware transport trajectories that are consistent with the phenoscape’s underlying geometry. GeoSinkhorn Flow can also model transitions directly between time points without constructing a phenoscape. GeoSinkhorn Flow uses heat-diffusion geometry to define manifold-aware transport costs and trains a geometric autoencoder whose latent Euclidean distances stay aligned with the static phenoscape geometry while extending it to unseen cells. By explicitly conditioning the learned transport dynamics on perturbation-specific gene or drug embeddings, GeoSinkhorn Flow generalizes its trajectories to new measurement conditions, produces intermediate progression states along a trajectory, and extends predictions to unseen cells and held-out perturbations. An unbalanced optimal transport variant further learns growth or transition weights, so that changes in relative cell-state abundance or transition propensity are modeled together with state movement. Across synthetic manifolds, patient-derived organoid drug responses, Perturb-seq knockdowns, and time-resolved CyTOF signaling, GeoSinkhorn Flow recovered intrinsic manifold geometry, inferred biologically coherent response trajectories, and generalized to held-out drug combinations, perturbation genes, and time points. Together, these results establish GeoSinkhorn Flow as a perturbation-conditioned, phenoscape-consistent dynamical framework, distinct from standard flow-matching approaches, for converting static phenoscapes into dynamic ones that generalize across experimental conditions. Abstract Figure: Overview of the GeoSinkhorn Flow pipeline. a) Single-cell measurements under control and perturbation conditions. b) Static phenoscape: each condition is one point representing its full cell distribution, and distances are Geodesic Sinkhorn (geodesic optimal transport) distances. c) Dynamic phenoscape: perturbation-conditioned trajectories carry the control population to each perturbation, and each trajectory is conditioned on its perturbation embedding c k . The inset shows single-cell trajectories under f θ ( z, c 1 , t ). d) Perturbation conditioning: drug and gene embeddings, with combinations composed from single agents, condition a flow over latent cell state z and progression t . This lets a single model predict a distinct trajectory for each perturbation, including held-out combinations (dashed).

  • Open Access

    Human claustrum neurons encode uncertainty and prediction errors during aversive learning

    by Mingyue Hu, Rodrigo Dalvit, Mauricio Medina-Pizarro, Maximilian Dougherty, Yajun Zhou, Jonathan Barreto-Nieves, Sami Obaid, Arman Afrasiyabi, Smita Krishnaswamy, Alfred P. Kaye, et al.

  • Open Access

    AI Scientists for Building Virtual-Cell Models

    by Mark Gerstein, Xiangru Tang, Jiapeng Chen, Yanjun Shao, Zhuoyun Yu, Yan Cui, Weixu Wang, Fang Wu, Yuxuan Liao, Yuchen Zhuang, et al.

    Autonomous agents, from virtual laboratories to biological data-analysis agents and co-scientists, have begun to turn scientific goals into hypotheses. Whether they can go further and convert real, noisy and complex biological data into executable model hypotheses and architectures that encode testable assumptions remains unclear. Predicting how cells respond to genetic and chemical perturbations (i.e., modeling virtual cells) is a natural test of this ability: it is central to decoding disease mechanisms and therapeutic discovery, yet it demands cross-disciplinary expertise rarely concentrated in a single research group. Here, we introduce CellForge, an organized team of autonomous agents for single-cell perturbation modeling. Given a dataset and a task, it surveys the literature, parses the data, identifies relevant baselines, and formulates a model hypothesis through critic-mediated discussion among agents specialized in data modeling, single-cell biology, and deep learning. It then writes the training code, runs the experiments, and returns a trained predictor including architecture, code, and validation results. The architecture itself is the hypothesis: CellForge produces it end-to-end, with no human specifying the design, loss, or training protocol. Across six perturbation datasets spanning transcriptomic, epigenomic, and proteomic contexts, CellForge yields models that are competitive with hand-crafted state-of-the-art results on established tasks and extends the same workflow to paired multiomic readouts. Blinded human evaluators rate CellForge’s research plans as more scientifically sound and innovative than those from single LLMs or deep-research systems. In summary, we show autonomous agents can complete the full hypothesis-to-validation cycle in single-cell biology, with an AI effectively building another AI, in a complex setting that currently requires a team of human experts.

  • Open Access

    Epithelial Stem Cell Fate Determines Chemoradiotherapy Response in Rectal Cancer

    by Nick Li, Fiza Ishaqwala, Thomas A. Wright, Alistair Wilkinson, Petra Vlckova, Katherine Trevers, Rhianna O’SUllivan, Shauna Crampsie, Ewa Basiarz, Sierra Vanderkamp, et al.

    SUMMARY: Rectal cancers are often treated with neoadjuvant chemoradiotherapy (CRT), yet 85% of patients do not achieve a pathological complete response. To identify the molecular determinants of CRT response, we profiled the single-cell signalling, DNA-damage, cell-cycle, apoptotic, and cell-fate responses of 2,769 patient-derived organoid cultures treated with CRT, cancer-associated fibroblasts (CAFs), and signal-rewiring agents. We find that CRT response is determined by stem cell-fate. CRT triggers comparable DNA-damage in isogenic proliferative (proCSC) and revival (revCSC) colonic stem cells, but proCSC retain damage and die whereas revCSC resolve damage and persist. Both CRT and CAFs drive proCSC to a common treatment-resistant revCSC fate and high revCSC predicts worse survival in patients. Pharmacologically constraining stem-cell plasticity increases CRT sensitivity, and Spatial Perturbation of ARrayed Tumour Assembloids (SPARTA) confirms YAP/TEAD inhibition improves chemotherapy responses in human stromal-tumour models. These results suggest that cancer cell-fate, not genotoxic damage itself, ultimately governs response to standard-of-care chemoradiotherapy. HIGHLIGHTS: Rectal cancer stem cell-fate determines chemoradiotherapy-induced apoptosis proCSCs retain DNA-damage and die, whereas revCSCs repair damage and persist CAFs and chemoradiotherapy converge on a common chemo-radioresistant revCSC state SPARTA reveals TEAD inhibition blocks DNA-repair persisters in stromal assembloids

  • Open Access

    Stromal Prostaglandin is a Dominant Spatial Regulator of Cell-fate Plasticity in Colorectal Cancer

    by Christopher Tape, Corinne Molyneux, Rhianna O'SUllivan, Eoghan Mulholland-Illingworth, Joshua Moore, Nick Li, Petra Vlckova, Raheleh Amirkhah, Aurélie Dobric, Shauna Crampsie, et al.

    Colorectal cancer (CRC) tumours with high stromal content have a worse outcome, but the mechanisms governing this are unclear. Using high-throughput single-cell perturbation analysis of CRC patient-derived organoids (PDOs) and cancer-associated fibroblasts (CAFs) we find that epithelial cells with high stromal-communication potential are marked by the transcriptional co-repressor DACH1 . To define the causal regulators of stromal-epithelial signalling, we developed a novel CRISPR screening platform to perturb the CAF secretome and measure epithelial stem cell responses at single-cell resolution. Intercellular CRISPR screening and full factorial ligand analysis revealed that stromal Prostaglandin E2 (PGE 2 ) is a dominant regulator of CRC cell-fate plasticity. Stromal PGE 2 converts DACH1 + epithelia from a chemosensitive proliferative colonic stem cell (proCSC) fate into a chemorefractory and pro-metastatic revival colonic stem cell (revCSC) fate. PGE 2 -driven epithelial transdetermination is rapid and reversible, providing an acute mechanism for stromal-driven plasticity in CRC tumours. Genetic and pharmacological inhibition of stromal COX2 inhibits epithelial plasticity, trapping CRC epithelia in an anti-metastatic and chemosensitive proCSC fate. PTGS2 + CAFs support a spatially resolved revCSC to proCSC plasticity gradient in human CRC tumours marked by increasing DACH1 expression. These results reveal that stromal prostaglandin is a dominant spatial regulator of poor-prognosis cell-fates and may explain the benefit of anti-COX therapies in both preventing and treating CRC.

  • Open Access

    Stromal Prostaglandin is a Dominant Spatial Regulator of Cell-fate Plasticity in Colorectal Cancer

    by Corinne Molyneux, Rhianna O'SUllivan, Eoghan J. Mulholland-Illingworth, Joshua W. Moore, Nick Li, Petra Vlckova, Raheleh Amirkhah, Aurelie Dobric, Shauna Crampsie, Alistair Wilkinson, et al.

    Colorectal cancer (CRC) tumours with high stromal content have a worse outcome, but the mechanisms governing this are unclear. Using high-throughput single-cell perturbation analysis of CRC patient-derived organoids (PDOs) and cancer-associated fibroblasts (CAFs) we find that epithelial cells with high stromal-communication potential are marked by the transcriptional co-repressor DACH1 . To define the causal regulators of stromal-epithelial signalling, we developed a novel CRISPR screening platform to perturb the CAF secretome and measure epithelial stem cell responses at single-cell resolution. Intercellular CRISPR screening and full factorial ligand analysis revealed that stromal Prostaglandin E2 (PGE 2 ) is a dominant regulator of CRC cell-fate plasticity. Stromal PGE 2 converts DACH1 + epithelia from a chemosensitive proliferative colonic stem cell (proCSC) fate into a chemorefractory and pro-metastatic revival colonic stem cell (revCSC) fate. PGE 2 -driven epithelial transdetermination is rapid and reversible, providing an acute mechanism for stromal-driven plasticity in CRC tumours. Genetic and pharmacological inhibition of stromal COX2 inhibits epithelial plasticity, trapping CRC epithelia in an anti-metastatic and chemosensitive proCSC fate. PTGS2 + CAFs support a spatially resolved revCSC to proCSC plasticity gradient in human CRC tumours marked by increasing DACH1 expression. These results reveal that stromal prostaglandin is a dominant spatial regulator of poor-prognosis cell-fates and may explain the benefit of anti-COX therapies in both preventing and treating CRC.


  • Human learning of noninvasive brain–computer interfaces via manifold geometry

    by Erica L. Busch, E. Chandra Fincke, Guillaume Lajoie, Smita Krishnaswamy, Nicholas B. Turk-Browne

    Brain-computer interfaces (BCIs) promise to restore and enhance human capabilities. Yet, their adoption has been limited by slow and inconsistent learning across users. We show that BCI learning is accelerated by leveraging the naturally occurring geometry, or intrinsic manifold, of brain activity, extracted using data diffusion. Participants were trained with real-time functional magnetic resonance imaging to control an avatar in a video game by self-modulating activity in brain regions supporting spatial navigation. We perturbed the mapping between brain activity and avatar movement to test how neural manifolds constrain human BCI learning. When new mappings relied on directions of significant variance on the intrinsic manifold, participants successfully gained control by realigning brain activity along these directions. When new mappings did not follow the intrinsic manifold, participants could not learn to control the avatar. These findings show how manifold geometry in higher-order brain regions guides human learning of complex cognitive tasks, identifying a principle for improving future neurotechnologies.


  • Open Access

    Beta cell-derived cholecystokinin drives obesity-associated pancreatic adenocarcinoma development

    by Cathy C. Garcia, Aarthi Venkat, Daniel C. McQuaid, Sherry S. Agabiti, Alexander Tong, Boby Mathew, Rebecca L. Cardone, Rebecca Starble, Christian F. Ruiz, Christy Zheng, et al.

    Pancreatic endocrine-exocrine crosstalk plays a key role in normal physiology and disease and can be altered by host metabolic states, such as obesity. Classically, endocrine islet beta (β) cell secretion of insulin is thought to promote the development of obesity-associated pancreatic adenocarcinoma (PDAC), an exocrine cell-derived tumor. Here, we show that β cell expression of the peptide hormone cholecystokinin (CCK) is necessary and sufficient for obesity-associated PDAC progression in mice and that CCK expression – rather than insulin – correlates strongly with enhanced tumorigenesis. Single-cell RNA-sequencing, in silico latent-space archetypal and trajectory analysis, and experimental lineage tracing in vivo reveal that obesity induces the expansion of postnatal immature β cells, which adapt to express CCK via stress-responsive JNK/cJun signaling. Finally, obesity perturbs CCK-dependent peri-islet exocrine cell transcriptional states and enhances islet-proximal tumor formation. These results define endocrine-exocrine CCK signaling as a bona fide driver of obesity-associated PDAC development and uncover avenues to target the endocrine pancreas to subvert exocrine tumorigenesis.


  • ImmunoStruct enables multimodal deep learning for immunogenicity prediction

    by Kevin Bijan Givechian, João Felipe Rocha, Chen Liu, Edward Yang, Sidharth Tyagi, Kerrie Greene, Rex Ying, Etienne Caron, Akiko Iwasaki, Smita Krishnaswamy


  • Open Access

    Supplementary Table 1 from AAnet Resolves a Continuum of Spatially Localized Cell States to Unveil Intratumoral Heterogeneity

    by Aarthi Venkat, Scott E. Youlten, Beatriz P. San Juan, Carley A. Purcell, Shabarni Gupta, Matthew Amodio, Daniel P. Neumann, John G. Lock, Anton E. Westacott, Cerys S. McCool, et al.

    Primary_replicate_differentially_expressed_genes